red-team
01Command
Red-team a RUNNING AI agent you own/are authorized to test; a finding is CONFIRMED only when the exploit's proof marker returns. Authorized, disposable-env testing only.
1 1mo ago A 37 tokens
original MIT
Open-source toolkit for AI agent security — autonomous attacker + static engine + scanner + red-team skills. Exploit-validated. trust-shell.com
Command
Red-team a RUNNING AI agent you own/are authorized to test; a finding is CONFIRMED only when the exploit's proof marker returns. Authorized, disposable-env testing only.
Command
Statically triage an AI agent's SOURCE for candidate vulnerable paths (RT-1..RT-9). Candidate != vuln — confirm with /red-team.